Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3478 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.5063. Min Range: -12.5063
Max Act: 12.5063. Min Act: -0.1700
Data Index: 5355366 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.5063. Min Range: -12.5063
Max Act: 12.4438. Min Act: -0.1700
Data Index: 3842416 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.5063. Min Range: -12.5063
Max Act: 12.0688. Min Act: -0.1700
Data Index: 2590914 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.9438. Min Act: -0.1699
Data Index: 1234599 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.9438. Min Act: -0.1700
Data Index: 5550280 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.7563. Min Act: -0.1700
Data Index: 1596407 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.6313. Min Act: -0.1700
Data Index: 8778647 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.6313. Min Act: -0.1700
Data Index: 2226262 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.5688. Min Act: -0.1700
Data Index: 5927462 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.5063. Min Act: -0.1700
Data Index: 2474917 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.4438. Min Act: -0.1700
Data Index: 469345 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.3813. Min Act: -0.1700
Data Index: 6353194 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.3813. Min Act: -0.1700
Data Index: 6616390 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.3188. Min Act: -0.1700
Data Index: 4558359 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.3188. Min Act: -0.1700
Data Index: 8493100 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.3188. Min Act: -0.1700
Data Index: 3441217 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.2563. Min Act: -0.1700
Data Index: 8026715 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.3188. Min Act: -0.1700
Data Index: 2680290 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.2563. Min Act: -0.1700
Data Index: 2584994 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.5063. Min Range: -12.5063
Max Act: 11.2563. Min Act: -0.1700
Data Index: 4805168 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19